• Subscribe
  • How to detect bots' comments in your PH discussion? πŸ€–

    I am here for answers. πŸ˜€ Daily, my conversations are flooded by fake profiles. (I am pretty curious how many I will be having under this post.) There are still some signs that detect them, but it is time-consuming and not so easy. This could help with detection: πŸ™„ Generic profile photo (saw profile photos of some celebrities). πŸ™„ That bot repeats keywords from your original post. πŸ™„ Non-sensical names. πŸ™„ They miss parts in the text (e.g. Our page [insert link]... :D) πŸ™„ Their profiles are without information. πŸ™„ If they have social media, they are empty as well. πŸ™„ Their Activity tab in profile: You can see many comments written at the same time (suspicious and impossible). What else?

    Replies

    CY Zhou
    Sometimes i use gpt to fix typos, and this makes my words sound like a bot! To avoid that, i force myself to be more tolerant to typos...
    Share
    Richard Reis
    Most Recommended Books
    Most Recommended Books
    Ah, good idea if someone wants to build a Product Hunt plugin πŸ‘€
    Share
    Richard Reis
    Most Recommended Books
    Most Recommended Books
    I also realized three things 1. Their replies are long/ verbose. 2. They'll summarize your post (e.g. "Great question Nika! Detecting bot comments is a real challenge especially as LLM technology proliferates bla bla bla") 3. The advice is generic (whereas you can tell when the advice is real because it contains some anecdote)
    Share
    AndrΓ© J
    I find it intriguing how GPT bots, with their remarkable ability to generate text, have become the virtual chameleons of conversation. Certainly, it's a marvel how they weave words into sentences that are both perplexing and delightful. What's more interesting is their knack for turning even the most mundane queries into epic narratives, replete with vocabulary that sounds like it was plucked straight from a thesaurus on a caffeine high. It's almost as if these bots attended a prestigious language academy in a parallel universe where the motto was, "Why say 'good' when you can say 'exceedingly superb'?" 😏
    Share
    AndrΓ© J
    @busmark_w_nika Which one? Bye bye bye? or was that n*sync πŸ€” (also please don't report my comment, I admit it, it was generated by a bot, I am guilty as charged πŸ˜‚)
    Share
    AndrΓ© J
    @busmark_w_nika I think I need to borrow a proper Sony discman w/ 10sec anti-skip-memory and AAA batteries. To really get the authentic experience and learn what you guys went through ^^
    Share
    AndrΓ© J
    @busmark_w_nika ..until we revive them all with AI and generate new albums πŸ˜…. #Ai era
    Share
    Tymek ZapaΕ‚a
    Thank you for this checklist, was looking forward for something like this. Bots are starting to be real pain in the ass. Sometimes I even wonder if it's the beginning of end of internet :( EDIT: I use AI heavily for myself for ideation and research but flooding forums with shitty comments is not the use of it I would ever approve
    Share
    Alexandre Contador
    Videco - AI Personalized Video
    Really needed it! It's funny when you see similar comments :p
    Share
    Kostya Bolshukhin
    What really scares me is when real people write like bots or worse.
    Share
    Kostya Bolshukhin
    This comment highlights the practical benefit of detecting comments from bots and uses an action verb hook to grab attention. It also mentions the target audience visitors to showcase relevance. "When you know β€” you know"
    Share
    mjkabir
    Comment Deleted
    Share
    Saif Ullah Khalid
    Let's see how many bots are going to post comments on this discussion... 🀣
    Share
    hafid Ahlaqach
    I was feeling the same thing. I think if you used LLMs enough you recognize their tone
    Share
    Ksenia Meshkova
    I wanted to add this point too, but then I realized that sometimes I use gpt to check my English grammar, and my message could sound like I'm a bot, but I'm not πŸ˜…πŸ˜…
    Share
    Konok Nazmul
    @kksrm use Gemini or Claude, the tone is better than GPT.
    Share
    hafid Ahlaqach
    @busmark_w_nika I asked for feedback on my project and i got this comment "Your project is like a finely crafted code - ready to launch and make waves in the digital world! Time to let it spread its tech wings and soar!" I am 99% sure it's generated by an LLM. for me when i am seeking human interaction i want to interact with other humans, share our thoughts ... comments like these are just meaningless
    Share
    hafid Ahlaqach
    @kksrm I think that's alright. I would prompt it to keep my voice and fix the grammar
    Share
    Tymek ZapaΕ‚a
    @hafid0x00 Yeah I wonder what was the person that gave this feedback thinking? Would he/she want to receive such meaningless "feedback" for their project...?
    Share
    Toni
    they paraphrase the original post and include words like : enhance, elevate, in the realm of, navigate, unleash, unlock, Harness.
    Share
    Alexandra Goss
    There are the whole networks of them Easy to spot if you check the Activity tab in their profile - they'll have the exact same product upvoted in the exact same order
    Share
    Kate Ramakaieva
    FuseBase /formerly Nimbus/
    @alex_skazka farmers 🀠
    Share
    Simona O'Neill
    Yeah I can definitely spot AI constructed comments too. Just by looking at the words they use. Totally over the top stuff like "your 1K kitty coins are like the digital equivalent of striking gold in a cat-filled mine!" πŸ˜‚πŸ˜‚πŸ˜‚
    Share
    Salar Davari
    nice one πŸ˜‚ sadly they're growing by hour!
    Share
    Yvik Ye
    Actually, many "High-Level" bots can act like real humans, making it difficult to figure them out. They often come with well-prepared fake profiles and even use generated real-life photos. πŸ˜‚
    Share
    Martin MaričÑk
    @xspiral @busmark_w_nika I don't think so Nika. Wasn't pointing at you at all! πŸ˜… Just saying there's a lot of AI generated, superficial content on PH posted by real humans.
    Share
    Martin MaričÑk
    @xspiral @busmark_w_nika On the flip side, some real humans can act like bots. πŸ€¦β€β™‚οΈ πŸ˜‚
    Share
    Alexander Grossman
    Sugar Free: Food Scanner
    Sugar Free: Food Scanner
    I recently tracked all launches and discussions over the past week and noticed a concerning trend. Many projects are inundated with the same bots in their launch discussions. Here’s what I observed: 1. Lack of Followers: These bots have very few followers, if any, and they are not following many others. 2. Poor Quality Photos: The quality of their profile pictures is very low, often pixelated and clearly not professionally made. 3. Template Names: They use names that follow repetitive, clichΓ©d templates. 4. No Social Links: There are no links to any social media profiles. 5. No Active Projects: They don't have any active projects listed. 6. Low Coins Level: Their coins level is either zero or very low, usually not exceeding white. 7. Incomplete Profiles: Their profiles are poorly filled out, with minimal information. 8. Short Activity Span: Their maximum activity streak is no more than two days. These patterns suggest that these bots are not genuine users but are being used to artificially inflate activity and support for various projects.
    Share
    Alexander Grossman
    Sugar Free: Food Scanner
    Sugar Free: Food Scanner
    I'm curious why anyone would create these bots to go around accounts and post comments in random discussions. Are they really trying to build activity in this way to use them for supporting unfair projects in the future?
    Share
    Alexander Grossman
    Sugar Free: Food Scanner
    Sugar Free: Food Scanner
    @busmark_w_nika Did someone create a profile that looks like it's real?
    Share
    Federico Zuluaga Knorr
    There is a great article by Krissy Davis on WeAreDevelopers "How to Tell if Something Was Written by ChatGPT" The main points for me: - Keywords like: β€œcutting-edge software” or "ever-evolving landscape" - Unusually formal tone in text that's meant to be conversational or casual - A remarkable absence of meaning in the comment 🧐
    Share
    Ksenia Meshkova
    Hey, Nika! Really good points, thank you! And what do you think? Do we need to report it if we're really sure that it is a bot? Once, I also had a comment that wasn't relevant to the discussion topic and asked me to open a strange link. I decided to report it. Do you think that was a good decision?
    Share